InferenceManage Inference

Configure Inference Timeouts

View as Markdown

NemoClaw uses separate time budgets for agent requests, local provider validation, sandbox readiness, and recovery. Change the budget that matches the phase that times out.

Choose the Timeout

Use the error location to select the correct setting.

SettingApplies toDefault
NEMOCLAW_AGENT_TIMEOUTOpenClaw per-request inference600 seconds
NEMOCLAW_LOCAL_INFERENCE_TIMEOUTOllama, vLLM, NIM, and compatible-endpoint validation during onboarding180 seconds
NEMOCLAW_SANDBOX_READY_TIMEOUTImage build, gateway upload, and in-sandbox boot after creation180 seconds
NEMOCLAW_GATEWAY_RECOVERY_WAIT_SECONDSOpenShell command re-registration after policy application, plus gateway health and re-registration during managed OpenClaw or Hermes recovery30, 90, or 120 seconds, depending on the recovery phase

The readiness timeout does not govern inference requests or provider validation.

NEMOCLAW_AGENT_TIMEOUT requires a positive integer; onboarding rejects any other value. NEMOCLAW_LOCAL_INFERENCE_TIMEOUT and NEMOCLAW_SANDBOX_READY_TIMEOUT accept finite, nonnegative seconds, round fractional values, and use their defaults for invalid or negative values. NEMOCLAW_GATEWAY_RECOVERY_WAIT_SECONDS accepts finite, nonnegative seconds and preserves fractional values. A valid value overrides the internal budget for the current recovery phase. An unset, blank, invalid, or negative value uses 30 seconds for OpenClaw gateway health, 90 seconds for Hermes gateway health, and 120 seconds for recreated-sandbox OpenShell registration when the recovery path does not supply another budget.

Increase the OpenClaw Request Timeout

Increase NEMOCLAW_AGENT_TIMEOUT for a slow model server, such as CPU-only local inference or modest vLLM hardware. NemoClaw writes this value to agents.defaults.timeoutSeconds and models.providers.<provider-id>.timeoutSeconds during onboarding.

$export NEMOCLAW_AGENT_TIMEOUT=1800
$nemoclaw onboard

This setting is baked into the sandbox image. Recreate an existing sandbox to apply a new value.

Increase the Local Validation Timeout

Raise NEMOCLAW_LOCAL_INFERENCE_TIMEOUT when the inference-server validation probe needs more than 180 seconds. Large prompts, cold local model loads, and slower hardware can require a larger budget.

$export NEMOCLAW_LOCAL_INFERENCE_TIMEOUT=300
$nemoclaw onboard

Local Ollama setup treats host-side curl timeouts as retryable probe failures and retries with a larger timeout before reporting validation failure. This variable does not extend the later sandbox-readiness wait.

Increase the Sandbox Readiness Timeout

Raise NEMOCLAW_SANDBOX_READY_TIMEOUT when onboarding creates the sandbox but image build, upload, or boot exceeds 180 seconds. This can occur during a first run with cold caches or on a remote VM over a slow link.

$export NEMOCLAW_SANDBOX_READY_TIMEOUT=600
$nemoclaw onboard

Increase the Recovery Wait

Set NEMOCLAW_GATEWAY_RECOVERY_WAIT_SECONDS when OpenShell needs more than 120 seconds to re-register the sandbox after onboarding applies policy presets.

Managed OpenClaw gateway health uses 30 seconds by default.

Set NEMOCLAW_GATEWAY_RECOVERY_WAIT_SECONDS before start or recover to extend the agent-specific gateway-health wait and, when recovery recreates the sandbox, the 120-second OpenShell re-registration wait.

$export NEMOCLAW_GATEWAY_RECOVERY_WAIT_SECONDS=300
$nemoclaw <sandbox-name> recover

A valid finite, nonnegative recovery override takes precedence over internal per-agent and per-call-site budgets.

Raise both onboarding budgets when the provider probe and the later sandbox creation phase are slow.

$export NEMOCLAW_LOCAL_INFERENCE_TIMEOUT=300
$export NEMOCLAW_SANDBOX_READY_TIMEOUT=600
$nemoclaw onboard

Apply Build-Time Changes

Recreate an existing sandbox when you change a timeout that NemoClaw bakes into its image.

$nemoclaw onboard --fresh --name <sandbox-name> --recreate-sandbox